Extractive summarization in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main goal of extractive summarization?

Choose the best description of extractive summarization.

A Generating a summary by selecting important sentences directly from the original text.

B Creating new sentences that paraphrase the original text to form a summary.

C Translating the original text into another language before summarizing.

D Removing all stop words and punctuation to shorten the text.

💡 Hint

Think about whether the summary uses original sentences or new ones.

Extractive summarization picks key sentences from the original text without changing them, unlike abstractive summarization which generates new sentences.

❓ Predict Output

intermediate

Output of sentence scoring in extractive summarization

What is the output of this code that scores sentences by word frequency?

NLP

text = "Machine learning is fun. Learning machines can improve. Fun machines learn fast."
words = text.lower().replace('.', '').split()
freq = {}
for w in words:
    freq[w] = freq.get(w, 0) + 1
sentences = text.split('. ')
scores = {}
for s in sentences:
    score = 0
    for word in s.lower().split():
        score += freq.get(word, 0)
    scores[s] = score
print(scores)

A SyntaxError due to missing colon in for loop

B {'Machine learning is fun': 9, 'Learning machines can improve': 8, 'Fun machines learn fast.': 8}

C {'Machine learning is fun': 7, 'Learning machines can improve': 7, 'Fun machines learn fast.': 7}

D {'Machine learning is fun': 6, 'Learning machines can improve': 6, 'Fun machines learn fast.': 5}

💡 Hint

Count how many times each word appears and sum for each sentence.

The code counts word frequencies and sums them per sentence. Words like 'machine' and 'learning' appear multiple times, increasing scores.

❓ Model Choice

advanced

Best model type for extractive summarization on long documents

Which model is best suited for extractive summarization of very long documents?

A A convolutional neural network designed for image classification.

B A simple logistic regression model using bag-of-words features.

C A transformer model with a long input window like Longformer or BigBird.

D A recurrent neural network without attention mechanisms.

💡 Hint

Consider models that handle long text efficiently.

Longformer and BigBird are transformer models designed to process long texts efficiently, making them suitable for extractive summarization of long documents.

❓ Metrics

advanced

Which metric best evaluates extractive summarization quality?

Choose the metric that best measures how well an extractive summary matches a human summary.

A BLEU score used mainly for machine translation.

B ROUGE score, which compares overlapping n-grams between summaries.

C Accuracy of a classification model on sentiment labels.

D Mean Squared Error between summary word counts.

💡 Hint

Think about metrics that compare text overlap.

ROUGE measures overlap of words and phrases between generated and reference summaries, making it suitable for extractive summarization evaluation.

🔧 Debug

expert

Why does this extractive summarization code produce empty summary?

Given the code below, why does the summary list remain empty after execution?

NLP

text = "AI is transforming industries. It helps automate tasks."
sentences = text.split('. ')
summary = []
for s in sentences:
    if 'machine' in s.lower():
        summary.append(s)
print(summary)

A Because none of the sentences contain the word 'machine', so the condition is never true.

B Because the split method removes the last sentence, leaving summary empty.

C Because the summary list is overwritten inside the loop instead of appended.

D Because the print statement is outside the loop and summary is not defined globally.

💡 Hint

Check the condition inside the loop and the text content.

The code checks if 'machine' is in each sentence, but the text does not contain 'machine', so no sentences are added to summary.